FR3055764A1 - METHOD FOR CONTROLLING THE REAL-TIME DETECTION OF A SCENE BY A WIRELESS COMMUNICATION APPARATUS, FOR EXAMPLE A CELLULAR MOBILE TELEPHONE, AND CORRESPONDING APPARATUS. - Google Patents

Abstract

The method for controlling the real-time detection of a scene by a wireless communication device equipped with at least one environmental measurement sensor, comprises a temporal adjustment (26) of the activation times (21) of said detection from measuring values (23) delivered by said at least one environmental measuring sensor (CPT1-CPT5) at measurement times (22).

Description

Holder (s): STMICROELECTRONICS (ROUSSET) SAS, STMICROELECTRONICS SA Société anonyme.

Extension request (s)

Agent (s): CASALONGA & ASSOCIES.

Pb METHOD FOR CONTROLLING DETECTION IN WIRELESS COMMUNICATION, FOR EXAMPLE A CORRESPONDENT.

REAL TIME OF A SCENE BY A CELL MOBILE TELEPHONE APPARATUS, AND APPARATUS

FR 3 055 764 - A1 (5 /) The method for controlling the real-time detection of a scene by a wireless communication device equipped with at least one environmental measurement sensor, comprises a time adjustment (26) of the instants of activation (21) of said detection from measurement values (23) delivered by said at least one environmental measurement sensor (CPT1-CPT5) at measurement instants (22).

i

Method for controlling the real-time detection of a scene by a wireless communication device, for example a cellular mobile telephone, and corresponding device

Embodiments and embodiments of the invention relate to controlling the detection in real time of a scene by a wireless communication device, for example a smart cellular mobile phone (“smartphone”) or even a tablet. digital, equipped with at least one environmental measurement sensor such as an accelerometer.

Certain wireless communication devices such as certain types of “smartphones” or tablets are capable today of performing scene detections which makes it possible to determine in which environment the user of the telephone or tablet is situated. This may allow a third party, for example an advertiser or a cultural organization, for example, to send relevant information in connection with the location of the user of the device.

Thus, for example if the user is located in a given tourist place, it can thus send him addresses of restaurant near the place where he is. Likewise, we can also send him information relating to certain monuments which are located near his place.

It is also possible to have certain settings made automatically by the phone (for example, using an audio sensor, it detects that the area is quiet and the phone itself goes into vibrate mode).

Currently, scene detection by the phone can be done at fixed intervals. However, this does not provide any flexibility which can lead to undue current consumption detrimental to the longevity of the phone battery.

Another solution may be to use the phone's GPS application to be able to locate the user and therefore the detected scene in real time.

However, here again, the use of the GPS function is detrimental to the consumption of the telephone.

There is therefore a need to improve decision-making regarding the detection of a scene by a wireless communication device, for example a cellular mobile phone or a tablet, which allows greater flexibility and has a reduced impact on current consumption.

And, according to one embodiment and embodiment, we will use the or at least some of the environmental measurement sensors (s) already generally present (s) on a cellular mobile phone or a tablet, for example an accelerometer and possibly a magnetometer or a gyroscope or an audio sensor, to determine the instants of activation of the detection of the scene.

Thus, according to one aspect, a method of controlling the detection in real time of a scene is proposed by a wireless communication device equipped with at least one environmental measurement sensor, the method comprising a temporal adjustment of the instants d activation of said detection from measurement values delivered by said at least one environmental measurement sensor at measurement instants.

By scene detection is meant in particular a discrimination of the scene in which the wireless communication device is located. Several known solutions exist for detecting (discriminating) a scene. These solutions use for example one or more dedicated sensors generally associated with a specific algorithm.

These sensors can be, in particular in applications requiring very little current consumption, for example accelerometers and / or gyroscopes and / or magnetometers and / or microphones. This is a multimodal approach. And in this case an example of a specific algorithm can be an algorithm implementing a binary decision tree on the basis of descriptors or attributes resulting from particular processing (for example filtering) on the raw data coming from the sensors. These descriptors can be, for example, means, energy values, variances, etc.

By environmental measurement sensor is meant in particular any type of sensor capable of providing information on the environment in which the wireless communication device is located, including for example spatiotemporal characteristics of the environment of the device, such as by example the temporally fixed nature or not of the environment, the speed of evolution of the spatiotemporal modification of the environment (from the detection of the movement of the device) and / or of the sound and / or spatial characteristics and / or visual of this environment, such as for example the noise level of the environment and / or the altitude and / or the brightness level of the environment (for example from sensors such as barometers, proximity sensors , optical sensors .....).

The sensor (s) used for detecting the scene may be different from the environmental sensor (s).

This being particularly in a context where the device is always on (Always-On) and where the battery life is an important criterion, at least one of the environmental sensors can also be a sensor used for detection scene. This may be the case, for example, but not limited to an accelerometer which can be used both as an environmental sensor to give an indication of the intensity of the movement of the device and as a sensor contributing to scene detection.

According to one embodiment, the method further comprises a determination of several criteria, typically at least two criteria, such as for example criteria defining the intensity of the movement of the device (telephone for example), from said values measurement and a temporal adjustment of said activation instants from these criteria.

The determination of these criteria can advantageously include an implementation of a classification algorithm or classifier, and preferably an implementation of a meta classification algorithm or meta classifier which performs for example a majority vote on the last five measurements in order to avoid outliers.

The method then advantageously comprises a temporal adjustment of the measurement instants from these criteria and a reinitialization of the determination of these criteria (reinitialization of the classifier for example) during each temporal adjustment of the measurement instants.

This temporal adjustment of the measurement instants can for example comprise an adjustment of the duration separating two successive measurement instants.

The instants of activation of the scene detection can be identical to the instants of measurement of the measurements delivered by the measurement sensors. This is particularly the case when environmental measurement sensors are also used for scene detection.

However, these activation times could be different from these measurement times, for example if different environmental sensors are used than those used for scene detection. Also, the method then comprises a temporal adjustment of the activation instants such as an adjustment of the duration separating two successive activation instants.

For example, we can increase the time interval between two measurement instants (or two activation instants) when there is little or no movement and we can decrease this time interval when the movement is large This allows you to effectively monitor changes in the environment of the phone when there is fast movement while saving power when the phone is not in motion.

Said at least one environmental measurement sensor can comprise at least one accelerometer.

It is also possible to use an environmental sensor of the audio sensor type, for example a microphone.

That said, the wireless communication device can be equipped with several environmental sensors and, in this case, a time adjustment of the instants of activation of said detection is advantageously carried out on the basis of measurement values delivered by said sensors at instants. of measurement.

The environmental measurement sensors can be chosen from the group formed by an accelerometer, a gyroscope, a magnetometer, an audio sensor, a barometer, a proximity sensor, an optical sensor.

In other words, one or more accelerometers can be used or else an accelerometer in combination with a gyroscope possibly in combination with a magnetometer or even more audio sensors or else one or more audio sensors in combination with one or more accelerometers, or else a gyroscope or a magnetometer.

According to another aspect, a wireless communication device is proposed, comprising detection means configured to detect a scene in real time, at least one environmental measurement sensor, and control means configured to effect a temporal adjustment of the instants. activating said detection from measurement values delivered by said at least one environmental measurement sensor at measurement instants.

The detection means can include the at least one environmental measurement sensor, and when there are several measurement sensors, at least some of the environmental measurement sensors.

According to one embodiment, the apparatus further comprises processing means configured to carry out a determination of several criteria from said measurement values and the control means are configured to effect said temporal adjustment of said activation times from said criteria.

The processing means may include a state machine implementing a classification algorithm, preferably a meta classification algorithm.

According to one embodiment, the apparatus further comprises control means configured to perform a temporal adjustment of the measurement instants from said criteria and to reinitialize the determination means during each temporal adjustment of the measurement instants.

The control means can be configured to adjust the duration between two successive measurement instants.

Furthermore, the control means can be configured to make an adjustment of the duration separating two successive activation instants.

When the device comprises several environmental measurement sensors, which can be chosen from the group formed by an accelerometer, a gyroscope, a magnetometer, an audio sensor, a barometer, a proximity sensor, an optical sensor, the control means are configured to perform a temporal adjustment of the instants of activation of said detection from measurement values delivered by said sensors at measurement instants.

Other advantages and characteristics of the invention will appear on examining the detailed description and modes of implementation and embodiments, in no way limiting, and the appended drawings in which:

- Figures 1 to 3 schematically illustrate different modes of implementation and embodiment of the invention.

In FIG. 1, the reference APP designates an electronic device, for example a wireless communication device equipped with an ANT antenna. This device can be a cellular mobile phone such as a smart phone (smartphone) or even a digital tablet.

The APP device here includes several environmental measurement sensors CPT1-CPT5, without this number being limiting.

As an indication, the sensors CPT1, CPT2, CPT3, CPT4, CPT5 can be chosen from the group formed by an accelerometer, a gyroscope, a magnetometer, an audio sensor such as a microphone, a barometer, a proximity sensor, a sensor optical.

Of course, the device can be equipped with several accelerometers and / or several gyroscopes and / or several magnetometers and / or several audio sensors and / or a barometer, and / or one or several proximity sensors, and / or one or more optical sensors.

At least one and in general at least some of these environmental measurement sensors can, in particular in a multimodal approach, form in combination with a conventional discrimination algorithm, for example of the binary decision tree type, intended to work by example on raw filtered data coming from these sensors, detection means configured to detect a scene. These means can thus for example detect if the APP device is located in such or such an environment (restaurant, moving vehicle, etc.).

Alternatively, the APP device could be equipped with a specific sensor, for example the CPT1 sensor, different from the environmental sensors mentioned above, for example a micro camera, capable of detecting a scene from the environment of the device .

This being in a context where the device is always on (Always-On) and where the battery life is an important criterion, it is preferable to use as sensors helping to detect a scene from the environment of the device, one or more sensors of the environmental type mentioned above.

It is now assumed by way of nonlimiting example that all of the environmental sensors CPT1-CPT5 contribute to the detection of the scene.

In addition to these sensors, the APP device includes a BLC block capable of cooperating with the CPTi sensors to process the detected scene and transmit the information via the ANT antenna of the device.

The device also includes MCTRL control means configured to perform a time adjustment of the instants of activation of scene detection from measurement values delivered by the environmental measurement sensors CPT1-CPT5 at measurement instants.

In this example, the instants of activation of the scene detection are the instants of measurement. However, in particular in a variant using a specific detection sensor, the instants of activation of the detection of the scene may be different from the instants of measurement.

The APP device also includes MTR processing means configured to determine here several criteria from the measurement values delivered by the CPT1-CPT5 sensors.

The APP apparatus also includes MCM control means configured to perform a temporal adjustment of the measurement instants from the determined criteria and, as will be seen below, reinitialize the determination means during each temporal adjustment of the measurement instants .

These different means BLC, MTR, MCTRL, and MCM are for example produced by software modules within the processor PR of the device APP.

Reference is now made more particularly to FIG. 2 to describe an embodiment of the method according to the invention.

As illustrated in FIG. 2, at activation times 21, a scene 20 is detected of the scene located in the environment of the device.

Furthermore, the CPTi sensors (i = 1 to 5) deliver measurements 23 at measurement instants 22. And, in a step 24, criteria are determined which will make it possible to carry out an adjustment 25 of these measurement instants.

In the case where the measurement instants correspond to the activation instants, the adjustment of the measurement instants corresponds to the adjustment of the activation instants.

If the activation instants are different from the measurement instants, then in step 26 the adjustment of the activation instants is carried out.

Reference is now made more particularly to FIG. 3 to describe an example of determining said criteria and of adjusting the instants of measurement.

This is implemented for example by a state machine. After an initialization phase 30, in a step 31, a default initial value for the time interval between two measurement instants is fixed. This initial default value can be of the order of a few seconds, for example 2, 4 or 6 seconds.

Then, at the end of each interval (step 32), the measurement values provided by the environmental sensors are acquired (step 33). And, in a step 34, a classification algorithm (classifier) is implemented which will determine here three criteria from the acquired measurement values, namely a first criterion C1 representative of an "absence of movement", a second criterion C2 representative of a "small movement" and a third criterion C3 representative of a "strong movement".

A classification algorithm or classifier is an algorithm well known to those skilled in the art. In this regard, a person skilled in the art may refer for all practical purposes, for example to the work of Jason Brownlee entitled "Master Learning Algorithms, discover how they work and implement them from scratch", 2016.

However, in the context of a particularly simple implementation, using few criteria, such as three criteria here, for example, a decision tree can be used as a classifier having completed a learning phase on a sensor measurement database. environmental. Such a decision tree is particularly simple to implement and requires ίο only a few bytes of memory and a working frequency of less than 0.01 MHz.

However, it is preferable to use a meta classification algorithm (or meta classifier) also well known to those skilled in the art who will, for example, carry out a majority vote on the last five measurements provided by the sensors, for example, to avoid outliers.

Depending on the criterion obtained at the end of step 34, three different values will be defined for the time interval separating two instants of measurement of the sensors.

Thus, in step 35 we can set a time interval value of the order of 10 seconds while we can set this value to 6 seconds in step 36 and two seconds in step 37.

In other words, the faster the movement, the more we will decrease the time interval between two instants of measurement.

In step 38, it is checked whether this time interval value has been modified compared to the previously stored value.

If this is the case, then in step 39, the classifier is reset before making a new determination of the criteria.

Otherwise, the classifier is not reset.

While we can use at least one accelerometer or even several accelerometers, we will have more details if we also use a gyroscope or even a magnetometer.

However, it can be particularly interesting to use audio sensors which are useful environmental descriptors. Indeed, if the device is not in motion, then the audio sensor can be useful to detect the nature of this environment. And, depending on the change in the audio environment, we can decide to increase or decrease the interval between the different measurement instants.

Of course, depending on the applications, one can use either environmental sensors of the accelerometer or gyroscope or magnetometer type, or audio sensors or a combination of these two types of sensors. This being in view of the simplicity of the classifier, one can advantageously choose not to use a multimodal approach for adjusting the measurement instants, that is to say not to use a combination of these two types of sensors.

In what has been described above, the adjustment of the time interval between the instants of measurement determines the periodicity of the detection of the scene.

This being the case, it would be possible, as a variant, to provide for at least 10 environmental sensors with regularly spaced measurement instants, for example every 20 ms for an accelerometer, and an adjustment of the periodicity, generally greater, of the instants of activation of the detection which is independent of this constant measurement interval, but which depends on the measurement values supplied by these sensors.

Claims (25)

1. Method for controlling the detection in real time of a scene by a wireless communication device equipped with at least one environmental measurement sensor, comprising a temporal adjustment (26) of the instants of activation (21) of said detection from measurement values (23) delivered by said at least one environmental measurement sensor (CPT1-CPT5) at measurement instants (22). 2. Method according to claim 1, further comprising a determination of several criteria (C1-C3) from said measurement values and a temporal adjustment of said activation times from said criteria. 3. Method according to claim 2, wherein the determination of said criteria (C1-C3) comprises an implementation of a classification algorithm. 4. Method according to claim 3, in which the determination of said criteria (C1-C3) comprises an implementation of a meta classification algorithm. 5. Method according to one of claims 2 to 4, further comprising a temporal adjustment of the measurement instants from said criteria and a reset (39) of the determination of these criteria during each temporal adjustment of the measurement instants. 6. Method according to claim 5, in which the temporal adjustment of the measurement instants comprises an adjustment (25) of the duration separating two successive measurement instants. 7. Method according to one of the preceding claims, in which the temporal adjustment of the activation instants comprises an adjustment (26) of the duration separating two successive activation instants. 8. Method according to one of the preceding claims, in which the measurement instants are identical to the activation instants. 9. Method according to one of the preceding claims, wherein said at least one environmental measurement sensor (CPT2CPT5) comprises at least one accelerometer. 10. Method according to one of the preceding claims, wherein said at least one environmental measurement sensor (CPT2CPT5) comprises at least one audio sensor. 11. Method according to one of the preceding claims, comprising, the wireless communication device being equipped with several environmental measurement sensors, a temporal adjustment of the instants of activation of said detection on the basis of measurement values delivered by said sensors (CPT1-CPT5) at measurement instants. 12. The method of claim 11, wherein said environmental measurement sensors (CPT1-CPT5) are chosen from the group formed by an accelerometer, a gyroscope, a magnetometer, an audio sensor, a barometer, a proximity sensor, a sensor. optical. 13. Wireless communication apparatus, comprising detection means (CPTi, BLC) configured to detect a scene in real time, at least one environmental measurement sensor (CPT1-CPT5), and control means (MCTRL) configured for perform a temporal adjustment of the instants of activation of said detection from measurement values delivered by said at least one environmental measurement sensor at measurement instants. 14. Apparatus according to claim 13, further comprising processing means (MTR) configured to perform a determination of several criteria from said measurement values and the control means are configured to perform said temporal adjustment of said activation instants to from these criteria. 15. Apparatus according to claim 14, wherein the processing means (MTR) comprise a state machine implementing a classification algorithm. 16. Apparatus according to claim 15, wherein the processing means (MTR) comprise a state machine implementing a meta classification algorithm. 17. Apparatus according to one of claims 14 to 16, further comprising control means (MCM) configured to carry out a temporal adjustment of the measurement instants from said criteria and to reinitialize the determination means during each temporal adjustment of the instants of measurement. 18. Apparatus according to claim 17, in which the control means (MCM) are configured to effect an adjustment of the duration separating two successive measurement instants. 19. Apparatus according to one of claims 13 to 18, wherein the control means (MCTRL) are configured to effect an adjustment of the duration separating two successive activation instants. 20. Apparatus according to one of claims 13 to 19, wherein said at least one environmental measurement sensor (CPT2-CPT5) comprises at least one accelerometer. 21. Apparatus according to one of claims 13 to 20, wherein said at least one environmental measurement sensor (CPT1-CPT5) comprises at least one audio sensor. 22. Apparatus according to one of claims 13 to 21, comprising several environmental measurement sensors (CPT1CPT5), and the control means (MCTRL) are configured to effect a temporal adjustment of the instants of activation of said detection from values measurement delivered by said sensors at measurement instants. 23. Apparatus according to claim 22, wherein said environmental measurement sensors (CPT1-CPT5) are chosen from the group formed by an accelerometer, a gyroscope, a magnetometer, an audio sensor, a barometer, a proximity sensor, a sensor optical. 24. Apparatus according to one of claims 13 to 23, wherein the detection means include at least one environmental measurement sensor (CPTi). 25. Apparatus according to one of claims 13 to 24 forming a cellular mobile phone or a digital tablet. 1/2 ΑΝΤ